UCP PlaygroundClaude Sonnet 4.6/Models/Claude Sonnet 4.6
InspectorAgentDocs
AnthropicAnthropic

Claude Sonnet 4.6

Anthropic's prior-generation balanced model (Sonnet 4.6, superseded by Sonnet 5), kept as a lower-cost option. Strong multi-turn checkout flow with wallet payment and identity linking support; higher token usage than Opus due to verbose tool responses.

Avg Tokens69,644Avg Duration33.8sTurns to Checkout8.5
CheckoutCartSearchTurnsTokens34.747.579.6440
Shopping Score38/100
Fair

Scores computed from real agent sessions against live UCP-enabled stores. Not estimated — every data point is from an actual tool call, checkout attempt, and store response.

Shopping Score Breakdown

Checkout Rate40%34.7%
Cart Rate20%47.5%
Search Rate10%79.6%
Turn Efficiency15%44%
Token Efficiency15%0%
19.6% of sessions failed with errors.

Top Stores

StoreCheckout %Cart %
www.everlane.com100%100%
houseofparfum.nl75.5%85.9%
forever21.com66.7%66.7%
••••••••••••••••62.5%62.5%
••••••••••••••••54.5%54.5%
reebok.com50%50%
westwing.de50%50%
mr-fothergills.co.uk50%50%
••••••••••••••••50%100%
••••••••••••••••50%100%

Known Issues

Nudge Dependencymedium

Stops after validation errors 9.3% of the time. Needs orchestrator nudge to continue checkout.

High Token Usagelow

Averages 67K tokens per session — highest among Anthropic models. Verbose tool response handling.

Meta Stringificationmedium

Frequently stringifies meta objects instead of passing as JSON. Requires orchestrator auto-injection for idempotency keys.

Token Usage

Avg per Session69,644
Fleet Average74,927
vs Fleet−7%
Median (p50)38,622
p90133,773
Prompt / Completion split
Prompt 68,300 (98%) Completion 1,063 (2%)
Daily Average Tokens (last 30 days)
Distribution range
Min0p2519,297p5038,622p7577,434p90133,773Max1,935,784

Test Claude Sonnet 4.6 on Your Store

Run a live agent session to see how Claude Sonnet 4.6 handles your store's checkout flow end-to-end.

Run Agent Session

Compare With Other Models

MetaMetaLlama 3.3 70B39.3%GoogleGoogleGemini 3.5 Flash38.1%AnthropicAnthropicClaude Sonnet 4.634.7%xAIxAIGrok 4.326.3%GoogleGoogleGemini 2.5 Flash23.3%AnthropicAnthropicClaude Opus 4.822.3%AlibabaAlibabaQwen 3.8 Flash22.2%DeepSeekDeepSeekDeepSeek V3.220.7%GoogleGoogleGemini 2.5 Pro19.8%GoogleGoogleGemini 3.1 Pro19.6%OpenAIOpenAIGPT-4o15%DeepSeekDeepSeekDeepSeek V4.1 Flash14.3%xAIxAIGrok 3 Mini (Reasoning)11.1%OpenAIOpenAIGPT-5.510.2%OpenAIOpenAIo4-mini (Reasoning)9.1%AnthropicAnthropicClaude Opus 59%xAIxAIGrok 4.58.1%AnthropicAnthropicClaude Sonnet 57.7%DeepSeekDeepSeekDeepSeek V4 Pro7.7%DeepSeekDeepSeekDeepSeek V4 Flash7.5%GoogleGoogleGemini 3.8 Flash6.7%DeepSeekDeepSeekDeepSeek R1 (Reasoning)3.6%Moonshot AIMoonshot AIKimi K33.1%AlibabaAlibabaQwen 3.7 Max2.6%MetaMetaLlama 4 Maverick2.3%GoogleGoogleGemini 3.6 Flash1.1%GoogleGoogleGemini 3.7 Flash0%OpenAIOpenAIGPT-6 Luna0%MetaMetaMuse Spark 1.30%AlibabaAlibabaQwQ 32B (Reasoning)0%
Full comparison view →